论文标题
Localbins：通过学习本地分布来改善深度估计
LocalBins: Improving Depth Estimation by Learning Local Distributions
论文作者
论文摘要
我们提出了一种新型的体系结构，以从单个图像中进行深度估算。该体系结构本身基于流行的编码器架构，该体系结构经常用作所有密集回归任务的起点。我们以Adabins为基础，该Adabins估计输入图像的深度值的全局分布，并以两种方式发展体系结构。首先，我们没有预测每个像素上本地社区的深度分布，而不是预测全球深度分布。其次，我们涉及解码器的所有层，而不是仅在解码器的末尾预测深度分布。我们称这个新的Architecture Localbins。我们的结果表明，在NYU-DEPTH V2数据集中，所有指标中的最新指标都有明显的改进。代码和预估计的模型将公开可用。
We propose a novel architecture for depth estimation from a single image. The architecture itself is based on the popular encoder-decoder architecture that is frequently used as a starting point for all dense regression tasks. We build on AdaBins which estimates a global distribution of depth values for the input image and evolve the architecture in two ways. First, instead of predicting global depth distributions, we predict depth distributions of local neighborhoods at every pixel. Second, instead of predicting depth distributions only towards the end of the decoder, we involve all layers of the decoder. We call this new architecture LocalBins. Our results demonstrate a clear improvement over the state-of-the-art in all metrics on the NYU-Depth V2 dataset. Code and pretrained models will be made publicly available.
